AI projects from Hugging Face

SlideOn

lightonai · Kit

An English sparse retrieval model from LightOn that turns queries and documents into sparse vectors for inverted-index search. It suits search engineers and de…

π₀.₅ (Pi05) (LeRobot)

lerobot · Kit

A robot control model that reads camera images, robot state and an optional instruction and outputs continuous actions. It is a base checkpoint for researchers…

Mimi

kyutai · Kit

A neural audio codec from Kyutai that squeezes speech into compact audio tokens and decodes them back. It suits researchers and developers building speech lang…

Rein-NPC-4B

jmc0 · Kit

Drives game characters that hold a conversation, take in-game actions such as selling an item or calling guards, and stay in character under pressure. For game…

Index-Translate-2B

IndexTeam · Kit

Translates text between 150 languages and follows instructions about glossaries, formatting, tone and length. A compact 2.3B model from IndexTeam for teams tha…

Ling-3.1-flash-1019

inclusionAI · Kit

Handles scientific and agentic tasks with 560B total and 25B active parameters and a 1M-token context, tuned further from Ling-3.1-flash. Serving examples use…

granite-speech-5.0-470m-turboctc

ibm-granite · Kit

Turns speech in seven languages into punctuated, capitalized text. A small 470M-parameter model from IBM Granite for fast transcription on servers, laptops and…

granite-speech-5.0-2b

ibm-granite · Kit

Turns speech into text in six languages and translates speech to and from English, with keyword biasing and language prompting. A compact 2B speech-language mo…

Granite-4.2-30B

ibm-granite · Kit

Works through a problem in steps before it answers, for math, code, tool calling and multilingual chat. IBM's largest dense Granite 4.2 model, under Apache 2.0…

SmolLM2-135M-Instruct

HuggingFaceTB · Kit

Answers chat-style questions and handles rewriting and summaries with a 135M-parameter instruction-tuned model small enough for on-device use. For developers w…

SmolLM2-1.7B-Instruct

HuggingFaceTB · Kit

Chats, rewrites and summarizes text and can call functions, in a compact 1.7B model small enough to run on-device. The instruction-tuned SmolLM2 from HuggingFa…

novel-humanize-4b

gugujiji · Kit

Rewrites Chinese web-novel chapters so they read less like AI output, keeping plot, dialogue and characters as they are. A 4B model built on Qwen3-4B, for non-…

gnani-evon-v3.3-30B-A3B

gnani · Kit

Chats, answers questions and reasons in English and ten Indic languages with a 128K context. A 30B mixture-of-experts model from Gnani.ai, for teams building a…

MANTA-27B

gevaertlab · Kit

Scores the answer options of medical questions from text or images in one pass, without writing text. A research model from Stanford's Gevaert Lab, not a medic…

Qwen3.8-27B-Randean-MXFP4

flechin · Kit

A 27B reasoning model tuned to answer plainly instead of hedging, quantized to MXFP4 so vLLM can serve it on a single 32 GB GPU, for developers who run local r…

UltraBERT-380M

dmis-lab · Kit

Predicts masked words in English text and gives you a pre-trained encoder with a 32K context to fine-tune for classification or retrieval. A fill-mask model fr…

DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw

ddalcu · Kit

Runs a pruned, 2-bit DeepSeek-V4.1-Flash on a 128 GB Mac through mlx-serve, keeping 192 of 384 experts and a 1M-token context. Strongest on code, reasoning and…

Chandra OCR 2

datalab-to · Kit

Reads text from images and PDFs and returns markdown, HTML or JSON that keeps the page layout. Handles handwriting, forms, tables and math in 90+ languages, fo…

cbx-indic-pii-extractor-58M

CobuildX-AI · Kit

Finds personal information such as names, phone numbers, Aadhaar and PAN in Indian-language and Indian English text and returns each value's position. The most…

rakedoc-nano-2

cloudraker · Kit

Parses document page images into text, tables and charts with markdown formatting. A 1.2B-parameter model with better chart extraction, for developers building…

FLUX.2 [klein] 4B Base

black-forest-labs · Kit

Makes and edits images from text prompts and reference pictures with an open 4B base model, built for fine-tuning, LoRA training and custom pipelines on one co…

FLUX 3 Image Klein Prompt Upsampler

black-forest-labs · Kit

A 9B model that turns a short image request, up to 10 reference images and optional bounding boxes into one detailed prompt for FLUX 3 Image Klein. For editing…

VoxLock

arbazsiddiqui · Kit

Keeps the caller's voice and removes other voices from call audio before speech-to-text hears them. A 27.3M-parameter open model that streams on a CPU, with fi…

Russian Emotional TTS

Andreevai · Kit

Speaks Russian text with emotion and marked word stress, and can copy a voice from a 3 to 10 second clip. Clone only voices you have the right to use.

Kolibri-1

Aleph-Alpha · Kit

Reasons and calls tools in German and English, with a context window of more than a million tokens. An open 78B mixture-of-experts model from Aleph Alpha that…

Africa TTS

AfriSpeech · Kit

Speaks text aloud in 92 African languages and English, faster than real time on a CPU, with voice cloning from a short clip. For developers and researchers who…

Spark-X2.6-4B-Base

XHToken · Kit

A 4.1B language model for on-device use, tuned for coding, agent tasks, long context and reasoning in English and Chinese, with three thinking levels. For deve…

Wan2.2-I2V-A14B

Wan-AI · Kit

Turns a still image into a video at 480P or 720P, using a Mixture-of-Experts design from Wan-AI. For creators and researchers who generate video from pictures.

Iris-3B by speridlabs

speridlabs · Kit

Generates 1024-pixel images from text prompts by painting every pixel directly, with no VAE or latent space. Fine-tuned versions estimate depth and restore or…

SenseNova-U1.5-8B-MoT-TailSteer

sensenova · Kit

An image generation and editing model that stays steadier across many successive edits, built on SenseNova-U1.5-8B-MoT with the same loading steps. For designe…

basal-omni-1.0-ultra

Remek · Kit

Answers typed questions about a message, document or agent trace with a calibrated probability for each allowed answer, in one pass without generating text. An…

BERT base model (uncased)

google-bert · Kit

Fills in masked words and extracts text features for English. The uncased BERT base model from Google, meant to be fine-tuned for classification, tagging and q…

Laya Multilingual

convaiinnovations · Kit

Reads text such as emails and tickets in 100+ languages and answers typed questions with probabilities in one pass. A 322M model, with no text generation, for…

DeepSeek-V4.1-Flash-1017 TrellisMX K2 Mix

brandonmusic · Kit

A compressed copy of DeepSeek-V4.1-Flash-1017 sized for two 96 GB GPUs, with a few experts stored at higher precision. A research build for people who serve la…

Jev-Omni

akhilaaa3 · Kit

Answers a question about text, an image, audio or video by giving a probability for each option you list, instead of writing an explanation. A 12B classifier b…

MiMo-V2.6-Flash-RL

XiaomiMiMo · Kit

Handles text, image, video and audio input in one model, with a 1M-token context for long repositories and agent runs. An open 311B mixture-of-experts model fr…

orukqwen-asr-1.7b

oruk · Kit

Turns English speech into text. It is Qwen3-ASR-1.7B post-trained by reinforcement learning on word error rate, for developers and speech researchers who need…

nomic-embed-text-v1.5

nomic-ai · Kit

Turns English text into embedding vectors for search, clustering and classification, and the vectors can be cut to a smaller size. It suits developers building…

Jasper-K-27B

ragentile · Kit

Reinforcement-learning tuned model for writing and speeding up GPU kernels, trained from a Qwen base with compile, correctness and timing feedback. For develop…

Qwen3.6-35B-A3B-FP8

Qwen · Kit

Reads text and images and writes text, as an FP8 copy of Qwen3.6-35B-A3B with 3B active parameters. For developers who run coding agents and want a smaller dow…

Qwen3.6-27B

Qwen · Kit

A 27B Qwen model that reads text and images and replies in text, tuned for coding agents and repository-level work, for developers who run it with the transfor…

Qwen3-Embedding-4B

Qwen · Kit

Turns text and code in over 100 languages into vectors for search, retrieval, classification and clustering, with adjustable vector size and task instructions,…

Qwen3-Coder-Next

Qwen · Kit

Works as a coding agent model with 80B total and 3B active parameters and a 256K context. For developers who run agents in CLI and IDE tools and want to host t…

Qwen3-4B-Instruct-2507

Qwen · Kit

Answers chat prompts with a 4B model that skips visible thinking and reads up to 256K tokens of context. For developers who want a small open assistant for rea…

Qwen2.5-Coder-7B-Instruct

Qwen · Kit

Writes, explains and fixes code as a 7B instruction-tuned member of the Qwen2.5-Coder family. For developers who want a capable open coding model that fits on…

Qwen2.5-1.5B-Instruct

Qwen · Kit

A small 1.5B chat model from Qwen that follows instructions, writes code and math, returns structured output such as JSON and handles over 29 languages. For de…

Hermes 4 14B

NousResearch · Kit

A 14B hybrid reasoning model from Nous Research, built on Qwen3-14B. It can think step by step, call tools, and return JSON that follows a schema. It uses the…

Hermes 3 Llama-3.1 8B

NousResearch · Kit

An 8B general-purpose chat model from Nous Research, built on Llama 3.1, with function calling, structured output, role play and code help. It suits developers…

Qwen3.5-9B Brainwaves DeepThought STEM OneJev1.6

nightmedia · Kit

An experimental 9.4B image-and-text model made by nightmedia, a merge of three 9B models aimed at reasoning and science questions. It suits hobbyists and resea…

Kronos-base

NeoQuasar · Kit

A 102M-parameter model for financial candlestick (K-line) data that forecasts price series and volatility and can generate synthetic data. Part of the Kronos f…

AREX-2-i1-GGUF

mradermacher · Kit

Weighted GGUF quantizations of BAAI/AREX-2, a 26.9B vision model, in about two dozen sizes from 7.2 GB to 22.2 GB, plus an imatrix file for making your own qua…

Qwen3.5-4B-3D-Html

mondk · Kit

A 4.2B text-generation model, fine-tuned from Qwen3.5-4B, that writes a 3D scene as one self-contained HTML file using Three.js. Open the file in a browser and…

harrier-oss-v1-0.6b

microsoft · Kit

Turns text in many languages into number vectors for search, clustering and similarity matching, a 0.6B embedding model from Microsoft for developers building…

MemT-1.0-Nano

MemTensor · Kit

Language model with a built-in memory state of fixed size, built on Qwen3.6-35B-A3B, that keeps past context without re-reading it. For researchers and develop…

Kev-4B

jaredpalmer · Kit

Reads a document and typed questions, then returns a calibrated probability for each answer option in one pass, without writing text. A Qwen3.5-4B based decisi…

Realtime-Venus

inclusionAI · Kit

Holds two 9B models for live conversation that listen and speak at the same time, handle interruptions and hand tasks to outside tools. One watches video and a…

Ming-3.0-audio-flash

inclusionAI · Kit

Listens to audio plus a text instruction and returns text, or text with synthesized speech. Covers speech recognition, spoken questions and audio reasoning in…

Hemmingway-1

HemmingwayAI · Kit

Writes everyday messages and emails as one ready-to-send text instead of a list of options. A 27B model built on Qwen3.8-27B, free for non-commercial use, for…

whisper-large-v3-chileno-lora

hablaip · Kit

A LoRA adapter that helps Whisper Large-v3 transcribe Chilean Spanish from real call center phone calls, with spontaneous speech, slang and line noise. Made by…

gemma-4-26B-A4B

google · Kit

Reads text and images and writes text, for developers who want an open-weights Google DeepMind model for coding, reasoning and image questions on their own GPU…

GLiNER2.5-Decide

fastino · Kit

Classifies English text against any label set you pass in, such as intent, routing, sentiment or urgency, in one pass with no prompt template. A small speciali…

Gadsby-4B

errrinn · Kit

Chats in a quirky chat-speak voice after a ban on word pairs common in Simple Wikipedia. A 4.3B-parameter Gemma 3 experiment for people curious about constrain…

Slonik

dglhf · Kit

Helps with agentic coding, with two models trained on PostgreSQL engine tasks. Slonik-27B and Slonik-9B come from Postgres Professional, for developers who wor…

Animagine XL 4.0

cagliostrolab · Kit

Generates anime-style images from tag-based text prompts, a Stable Diffusion XL fine-tune retrained on a large anime dataset. For artists and developers using…

joey-1

baselabs · Kit

Returns calibrated probabilities for yes-or-no, multiple-choice and scored questions about a text or an image, from one 2B model. For teams that route, triage…

AsteroRank-Lepton

Asteromorph · Kit

Scores how relevant each document is to a search query, with optional context, to reorder search results. A 4B open-weights reranker for science and general se…

Chronos-2

amazon · Kit

Forecasts time series without any training on your data, covering single series, many related series and series with extra inputs. A 120M-parameter model from…

MOSS-Image-SFT-4-steps

akhaliq · Kit

Makes the MOSS-Image-SFT text to image model finish a picture in 4 steps with no guidance, using one LoRA file. Renders English and Chinese text, for ComfyUI a…

Drone Transcripter 4

AbdelrhmanX2 · Kit

Turns Egyptian Arabic speech into text, tuned on classroom lectures and also covering everyday speech and Arabic-English mixing. For anyone transcribing Egypti…

Sekai-1

8BitStudio · Kit

A 95.6M-parameter English chat model trained from scratch on one RTX 5060 Ti, small enough to run on a CPU. For people who want a tiny local language model to…

Xing4.0-29B-A4B

XingChen-AGI · Kit

Generates text and works through multi-step jobs such as planning and tool calls, in English and Chinese, with a 256K context window. A mixture-of-experts mode…

Wan2.1-T2V-1.3B

Wan-AI · Kit

Makes short 480P videos from a text prompt, small enough for most consumer GPUs with about 8 GB of video memory. For creators and researchers who want local te…

d3-flash

vllm-sr · Kit

A 9B model that answers several choice, yes or no and score questions about text, images or video in one call, returning a probability for every answer instead…

d3

vllm-sr · Kit

Answers choice, yes-or-no and score questions about text, images or video in one call, returning a probability for each answer instead of text. A 27B decision…

mai_replier-9b-v3

tcmofashi · Kit

Plays a persona in Chinese QQ group chats by reading the chat history and writing one short, casual reply with no visible reasoning. A merged 9B fine-tune of Q…

strands-decider-2B-qwen3.5-v1-2610

StrandsAgents · Kit

Makes fast decisions for agent workflows by picking among options and rating things on a scale, with a calibrated confidence for every answer. For developers w…

gemma-4-12b-constraintkit

shib79 · Kit

A 12B Gemma fine-tune that turns plain English into a parts-and-mates program for the constraint-kit CAD system, and says so when a request is out of scope, fo…

Qwen3.5-35B-A3B

Qwen · Kit

A multimodal chat model that reads images and text, with 35B parameters of which 3B are active at a time. For developers who host their own large model with Tr…

Qwen3.5-27B

Qwen · Kit

Reads text and images and writes text, as a 27B Qwen model with a vision encoder and a 262,144-token native context. For developers who build assistants and ag…

Qwen3-Reranker-0.6B

Qwen · Kit

Scores how well each passage answers a query, to put the best passages first in search and retrieval systems. A 0.6B text reranking model covering over 100 lan…

Qwen3-0.6B-Base

Qwen · Kit

Provides Qwen3-0.6B-Base, the small pretrained base model of the Qwen3 family, trained on 119 languages with a 32k context. For developers who fine-tune or stu…

VieNeu-TTS v3 Turbo

pnnbao-ump · Kit

Speaks Vietnamese and English at 48 kHz with 23 preset voices from three regions, instant voice cloning and real-time streaming. A small 131M text-to-speech mo…

ARLoop-1.2B

osunlp · Kit

An open 1.2B base language model from osunlp, a looped transformer with attention residuals, released with checkpoints from a 500B-token training run. For text…

MiniCPM-OCR Jev

openbmb · Kit

Scores how likely an OCR result for a text, formula or table region is correct, from 0 to 1. For teams that auto-accept good results, send the rest to review o…

Mithi v2 Flash

Oomni · Kit

Reads text aloud in 11 Indian languages, English included, with 10 voices, from a 199 MB model that runs on a GPU or a plain CPU. For developers who need small…

DeepSeek-V4.1-Flash-1017-NVFP4

nvidia · Kit

NVIDIA's NVFP4 quantized copy of DeepSeek AI's DeepSeek-V4.1-Flash-1017, a huge multimodal mixture-of-experts model for NVIDIA Blackwell GPUs.

Qwen3.8-27B-4bit (MLX)

mlx-community · Kit

4-bit MLX conversion of Qwen3.8-27B that reads text and images and answers in text, run with the mlx-vlm tool. For developers who want to run a vision-language…

Mistral-7B-Instruct-v0.3

mistralai · Kit

A 7.2B open chat model from Mistral AI that follows instructions and can call functions you describe. It is fine-tuned from Mistral-7B-v0.3 and runs with mistr…

mine-embed-v1

MineAITechnology · Kit

Scores how close two short English texts are in meaning with a small 57.8M embedding model trained from scratch, an early experiment for people who study or ba…

Mage-VL

microsoft · Kit

A Microsoft multimodal model for images and video that reads video the way a codec stores it, keeping only the patches that change. It suits developers and res…

DeepSeek-V4.1-Flash-1017 EXL3 EAQ v1 2.9 bpw

Mia-AiLab · Kit

A 2.9 bits-per-weight EXL3 quantization of DeepSeek-V4.1-Flash-1017 that reads text and images. It cuts the model to about 210 GB for exllamav3 runtimes, and t…

MOSS-Image-Base 8-step data-space DMD

lodestones · Kit

A work-in-progress distillation of MOSS-Image-Base that draws an image in 8 steps with no guidance, shipped as a LoRA and a data-space sampler. For people expe…

CLAP2-L

laion · Kit

A 340M-parameter audio-text model from LAION that places sounds and English text in one embedding space, for zero-shot audio classification, audio-text search…

Laplace-1-Vector by JuneoAI

JuneoAI · Kit

Judges which action an AI agent should take, who should own a task and who may see what, as a 4B model that runs on your own hardware so organizational data st…

Mellum2.1-12B-A2.5B-Thinking

JetBrains · Kit

A 12B mixture-of-experts thinking model with 2.5B active parameters, trained with reinforcement learning on real repositories for coding agents, math and hard…

Ling-3.1-flash

inclusionAI · Kit

Handles complex agent, search, office and coding work with 560B total and 25B active parameters and a 1M-token context. Serving examples use SGLang on multi-GP…

K2-Horizon-7B

IFM · Kit

Writes text, code and reasoning answers with a 512K-token context window, for developers and researchers who want an open dense model whose training data, code…

Granite-4.2-8B

ibm-granite · Kit

Reasons step by step, writes code, calls tools and chats in several languages with a context of up to 128K tokens, extendable to 512K. IBM's dense 8B model, fo…

SmolLM3-3B

HuggingFaceTB · Kit

Writes text and answers questions as a small 3B open model with switchable step-by-step thinking, tool calling and long context, for developers who want a comp…

Qwen3.8-27B QSA BF16

higa2515 · Kit

BF16 source weights of Qwen3.8-27B with learned sparse attention indexers added, plus a reference Transformers loader, for people studying or deploying Qwen Sp…